Skip to content
AI Atlas
PaperActive

Characterizing Bluesky Content Moderation Service: From Automation of Service to Landscape of Harms

arxiv.org/abs/2609.11373

quality89

Updated 42 min ago · first seen 12 Sept 2026

paper_01M29X34XGAM4P4GBD9SBG8X4A

Published
12 Sept 2026
T1 · 43 min ago
arXiv
2609.11373
T1 · 43 min ago
Category
cs.CY
T1 · 43 min ago

Abstract

Empirical research on content moderation is fundamentally constrained by the opaque deployment of moderation systems on major social media platforms. To this end, the recent emergence of decentralized platforms with transparent, public moderation logs presents an unprecedented opportunity for independent audits. In this work, we leverage this architectural transparency to conduct the first large-scale audit of the default moderation system on Bluesky, the Bluesky Moderation Service (BMS). Analyzing its 10.6M moderation labels from 2025, we investigate three foundational aspects: (i) its mechanism (the degree of automation versus human oversight), (ii) its efficacy (accuracy in detecting harms), and (iii) its purpose (the landscape of harms it identifies). Our findings reveal a human-AI collaborative system where labels for sexual and graphic content are applied automatically in seconds, while nuanced and high stakes labels require more human oversight, taking hours or days. Through a manual annotation study, we find the BMS operates with high precision (0.837), but struggles with low recall (0.222), with our annotators identifying 4.5$\times$ more harmful content than the moderation system in a random sample. Finally, unsupervised clustering of the most frequently applied labeled posts uncovers detected harms ranging from hostility in discourse toward protected groups to the spread of sexually explicit and other graphic content. Our work offers a look into the operational realities of a deployed moderation system, providing a concrete data-driven foundation for designing more effective and transparent moderation systems.

Authors 8

Abhijnan Chakraborty, Abhisek Dash, Ayan Majumdar, Ingmar Weber, Krishna P. Gummadi, Pushpdeep Singh, Sayeh Jarollahi, Vabuk Pahari

Specification

Official page

Source:arXiv (Atom API + RSS)T1observed 43 min agohigh

Arxiv announce type
cross

Source:arXiv (Atom API + RSS)T1observed 43 min agohigh

arXiv id
2609.11373

Source:arXiv (Atom API + RSS)T1observed 43 min agohigh

Categories
cs.AI, cs.CY

Source:arXiv (Atom API + RSS)T1observed 43 min agohigh

PDF

Source:arXiv (Atom API + RSS)T1observed 43 min agohigh

Primary category
cs.CY

Source:arXiv (Atom API + RSS)T1observed 43 min agohigh

Published
12 Sept 2026

Source:arXiv (Atom API + RSS)T1observed 43 min agohigh

Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →

Provenance

Attributed facts

9

Source tiers

T19

Freshest observation

43 min ago

Conflicts

None